toolings

InterpretML

Microsoft

TOOLKIT

Fit interpretable models. Explain blackbox machine learning...

toolings

FairML: Auditing Black-Box Predictive Models

TOOLKIT

We present FairML, an end-to-end toolbox for auditing predictive models by quantifying the relative significance of the model’s inputs. FairML leverages model compression and four input ranking algorithms to quantify a model’s relative predictive dependence on its inputs...

toolings

FairLean

Microsoft Research

PACKAGE

A Python package to assess and improve fairness of machine learning models.

toolings

Eli5

LIBRARY

A library for debugging/inspecting machine learning classifiers and explaining their predictions

toolings

Fairness Comparison

TOOLKIT

Comparing fairness-aware machine learning techniques...

toolings

Fairness in Classification

RESEARCH

In this paper, we introduce a new notion of unfairness, disparate mistreatment, which is defined in terms of misclassification rates. We then propose intuitive measures of disparate mistreatment for decision boundary-based classifiers, which can be easily incorporated into their formulation as convex-concave constraints. Experiments on synthetic as well as real world datasets show that our methodology is effective at avoiding disparate mistreatment, often at a small cost in terms of accuracy...

toolings

eXplainability Toolbox

The Institute for Ethical AI & Machine Learning

TOOLKIT

XAI - An eXplainability toolbox for machine learning

toolings

Remove problematic gender bias from word embeddings

RESEARCH

The blind application of machine learning runs the risk of amplifying biases present in data. Such a danger is facing us with word embedding, a popular framework to represent text data as vectors which has been used in many machine learning and natural language processing tasks. We show that even word embeddings trained on Google News articles exhibit female/male gender stereotypes to a disturbing extent. This raises concerns because their widespread use, as we describe, often tends to amplify these biases...

toolings

Data Ethics Workbook for Public Sector

UK Department for Digital Culture Media & Sport

The Data Ethics Workbook will help you decide how you to align your work with the Data Ethics Framework principles. It will help you design an implementation plan for managing high quality results and mitigating risks...

toolings

Aequitas

Center for Data Science and Public Policy – University of Chicago

TOOLKIT

An open source bias audit toolkit for machine learning developers, analysts, and policymakers to audit machine learning models for discrimination and bias, and make informed and equitable decisions around developing and deploying predictive risk-assessment tools...